Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194659" target="_blank" >RIV/00216208:11320/13:10194659 - isvavai.cz</a>
Result on the web
<a href="http://aclweb.org/anthology/P/P13/P13-1028.pdf" target="_blank" >http://aclweb.org/anthology/P/P13/P13-1028.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Stop-probability estimates computed on a large corpus improve Unsupervised Dependency Parsing
Original language description
Even though the quality of unsupervised dependency parsers grows, they often fail in recognition of very basic dependencies. In this paper, we exploit a prior knowledge of STOP-probabilities (whether a given word has any children in a given direction), which is obtained from a large raw corpus using the reducibility principle. By incorporating this knowledge into Dependency Model with Valence, we managed to considerably outperform the state-of-the-art results in terms of average attachment score over 20treebanks from CoNLL 2006 and 2007 shared tasks.
Czech name
—
Czech description
—

Project
<a href="/en/project/DF12P01OVV022" target="_blank" >DF12P01OVV022: ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)</a><br>
Continuities
V - Vyzkumna aktivita podporovana z jinych verejnych zdroju

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics
ISBN
978-1-937284-50-3
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
281-290
Publisher name
Association for Computational Linguistics
Place of publication
Sofija, Bulgaria
Event location
Sofija, Bulgaria
Event date
Aug 4, 2013
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)